Bentley Communities
Bentley Communities
  • Site
  • User
  • Site
  • Search
  • User
ContextCapture | Descartes | Pointools | Orbit
  • Product Communities
ContextCapture | Descartes | Pointools | Orbit
ContextCapture | Descartes | Pointools | Orbit Wiki iTwin Capture detectors download page
    • Sign In
    • +Reality Modeling Wiki
    • +Bentley I/RAS B
    • +Bentley LumenRT
    • +Bentley Pointools
    • -ContextCapture -
      • +ContextCapture User Guides
      • +ContextCapture - Release information
      • +ContextCapture Technical Previews
      • +ContextCapture - How to
      • ContextCapture Frequently Asked Questions
      • +ContextCapture - Troubleshooting
      • -ContextCapture Insights
        • iTwin Capture detectors download page
        • Link to download ContextCapture Detectors in Update 18 not working
      • ContextCapture License Options
      • Describe the Different Modules of ContextCapture
      • What are the different editions of ContextCapture?
      • ContextCapture User Requirements
    • +Descartes and ContextCapture Editor(deprecated product)
    • +Orbit 3DM
    • +RealityModeling Cloud Services

    You are currently reviewing an older revision of this page.

    • History View current version

    Context Insights detectors download page

    Here is a list of detectors already trained. They can be executed in ContextCapture and ContextCapture Center Master to run Annotation jobs.
    Each detector was trained:

    • For a specific purpose
    • On a specific dataset

    Meaning, while running on your dataset, each detector type can only be used for the same specific type of job (Annotation job type).


    The quality of the detection will depend on the similarity between your dataset and the training dataset’s description.

    Please make sure to download detectors matching your ContextCapture version. 
    We recommend you to update to latest

    In case no detector fits your purpose, you are welcome to submit a help ticket from your personal portal describing your expectations.

    Image – 2D Objects / 3D Objects detectors

    Annotation job type

    Name & Purpose

    ContextCapture version

    Description of training dataset

    Illustration

    2D Objects


    3D Objects


    3D Segmentation*

     

     

    *only as a secondary tool for optimization

    Coco

    90 classes for everyday life objects: cars, books, chairs, etc…

    Update 19

    Images: Handheld

    Resolution: Not available

    Region: multiple

     

      

    Antennas_v1

    1 class for antennas mounted on towers

    Update 19

    Images: Drone


    Resolution: around 1cm/pix


    Region: Multiple

      

    Faces & License plates

    1 single class to group faces and license plates and support anonymization workflows

    Update 19

    Images: Mobile mapping device - Panoramas

    Resolution: N/A

    Region: Western Europe

      

    Image – 2D Segmentation detectors

    Annotation job type

    Name & Purpose

    ContextCapture version

    Description of training dataset

    Illustration

    2D Segmentation

     

    Segmented mesh

     

    Mesh patches

    Cracks

    1 class for cracks in concrete infrastructure

    Update 19

    Images: Drone + Handheld

    Resolution: around 1cm/pix

    Region: multiple

     

      

    Pascal

    20 classes for everyday life elements: cars, motorbikes, persons, etc…

    Update 19

    Images: Handheld

    Resolution: Not available

    Region: multiple

      

     

    Pointcloud (possibly derived from image-based mesh) – 3D Segmentation detectors

    Annotation job type

    Name & Purpose

    ContextCapture version

    Description of training dataset

    Illustration

    3D Segmentation

    Buildings A

    1 class for buildings in city environment

    Update 19

    Pointcloud: RGB - Derived from aerial photogrammetry

    Resolution: 20cm

    Region: Graz - Western Europe

     

      

    Ground Occupation

    5 classes in city environment: Roofs, vegetation, bridges, power lines, ground

    Non-Commercial use

    Update 19

    Pointcloud: RGB - Aerial Lidar

    Resolution: 20cm

    Region: Strasbourg - Western Europe

      

    Ground Occupation + 3D objects:

    Segmentation-5 classes:
    Ground, vegetation, power lines, buildings, fences

    3D objects:
    Trucks, cars, poles

    Non-Commercial use

    Update 19

    Pointcloud: Non colorized - Aerial Lidar

    Resolution: 5cm

    Region: Dayton - North America

      

    Ground Occupation + 3D objects:

    Segmentation-6 classes:
    Urban furnitures, roofs, facades, trees, shrubs, vertical surfaces

    3D objects:
    Chemineys, vehicles 

    Non-Commercial use

    Update 19

    Pointcloud:RGB - Aerial Lidar

    Resolution: 10cm

    Region: Hessigheim - Western Europe

      

    Rail


    9 classes for usual rail assets: Rails, Signals, PointSensors, etc…

    Update 19

    Pointcloud: RGB - Mobile mapping system

    Resolution: 3cm

    Region: Western Europe

     

      

     

    Orthophoto - Segmented orthophotos detectors

    Annotation job type

    Name & Purpose

    ContextCapture version

    Description of training dataset

    Illustration

    Segmented orthophotos

    Roofs – A

    1 class for building roofs in city environment

    Update 19

      

    Images: Vertical - aerial mapping camera

    Resolution: around 30cm/pix

    Region: Multiple

       

    Roofs – B

    1 class for building roofs in city environment

    Non-Commercial use

    Update 19

    Images: Vertical - aerial mapping camera

    Resolution: around 7.5cm/pix

    Geographic area: Christchurch - New Zealand

     

      

    City - A

    6 classes for buildings, High vegetation, low vegetation, vehicles, roads

    Non-Commercial use

    Update 19

    Images: Vertical - aerial mapping camera

    Resolution: 5cm/pix

    Geographic area: Potsdam - Western Europe

     

    Orthophoto + DSM - Segmented orthophotos detectors

    Annotation job type

    Name & Purpose

    ContextCapture version

    Description of training dataset

    Illustration

    Segmented orthophotos

    City - A

    6 classes for buildings, High vegetation, low vegetation, vehicles, roads

    Update 19

    Images: Vertical - aerial mapping camera

    Resolution: 5cm/pix

    Geographic area: Potsdam - Western Europe

     

         

    Communities
    • Home
    • Getting Started
    • Community Central
    • Products
    • Support
    • Secure File Upload
    • Feedback
    Support and Services
    • Home
    • Product Support
    • Downloads
    • Subscription Services Portal
    Training and Learning
    • Home
    • About Bentley Institute
    • My Learning History
    • Reference Books
    Social Media
    •    LinkedIn
    •    Facebook
    •    Twitter
    •    YouTube
    •    RSS Feed
    •    Email

    © 2023 Bentley Systems, Incorporated  |  Contact Us  |  Privacy |  Terms of Use  |  Cookies